眼动交互的实时线性算法构造和实现  

Research and Realization on Real-time Linear Prediction Algorithm for Desktop Eye-Tracking

作　　者：程成[1] 杜菁菁[1] 蓝飞翔[1] 

机构地区：[1]北京理工大学计算机科学技术学院,智能信息技术北京市重点实验室,北京100081

出　　处：《电子学报》2009年第B04期12-15,共4页Acta Electronica Sinica

基　　金：国家自然科学基金(No.60773046);国家863高技术研究发展计划(No.2006AA01Z120);北京市重点学科项目

摘　　要：眼动跟踪技术作为一种新兴的交互手段,具有自然、高效和易于意图理解等优点.我们设计实现了一个桌面眼动跟踪系统作为虚拟装配系统的一个通道,通过摄像机实时采集视频并经过实时的图像处理判断用户对虚拟环境中对象的注视焦点.系统利用了瞳孔-角膜反射向量法理论,设计和实现了一个高效的实时眼动跟踪算法,即线性逼近预测算法.实验证明这一方法很好的解决了眼动通道的实时性问题.Eye-tracking as a new method of human computer interaction has the merits of naturalness, efficiency and easy intent understanding. The authors have designed a Desktop Eye-Tracking System which used the technique of image processing to obtain the user＇s gaze focus in virtual environment scene. Based on the theory of pupil center corneal reflection, the authors improved and realized a highly efficient linear prediction algorithm for real-time eye gaze image processing. Experiments proved that this algorithm can well support real-time eye-tracking as an interaction modality for desktop virtual environment.

关 键 词：眼动跟踪 人机交互 线性逼近预测算法 瞳孔-角膜反射向量法 

分 类 号：TP334.22[自动化与计算机技术—计算机系统结构]